AI agents call vibekit_get_app to retrieve information from Vibekit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple data retrieval operation without any capability to modify, delete, or execute operations on the app. It only fetches informational metadata about app properties. The worst-case misuse would be information disclosure about app configuration, which is a low-severity outcome.
From the tool's definition Tool retrieves details about a hosted app including 'status, URL, plan, and usage'—all read-only query operations with no modification, deletion, or execution of side effects.
Attacks that exploit this kind of access
Get details about a specific hosted app including status, URL, plan, and usage. It is categorised as a Read tool in the Vibekit MCP Server, which means it retrieves data without modifying state.
Register the Vibekit MCP server in PolicyLayer and add a rule for vibekit_get_app: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Vibekit. Nothing to install.
vibekit_get_app is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the vibekit_get_app rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for vibekit_get_app. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
vibekit_get_app is provided by the Vibekit MCP server (vibekit-apps/vibekit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →